From c81598897f55c486ce32b13a5f3ea101f5a04b07 Mon Sep 17 00:00:00 2001
From: Le Ma <le.ma@amd.com>
Date: Fri, 22 Nov 2019 17:56:47 +0800
Subject: drm/amdgpu: clear ras controller status registers when interrupt
Git-commit: 28f87950d935eec2ba1076933535213f4f5c8a06
Patch-mainline: v5.6-rc1
References: jsc#SLE-12680, jsc#SLE-12880, jsc#SLE-12882, jsc#SLE-12883, jsc#SLE-13496, jsc#SLE-15322
occurs
To fix issue that ras controller interrupt cannot be triggered anymore after
one time nbif uncorrectable error. And error count is stored in nbif ras object
for query.
Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 25231d699341..9a3a65a0691c 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -52,6 +52,9 @@
#define BIF_MMSCH1_DOORBELL_RANGE__OFFSET_MASK 0x00000FFCL
#define BIF_MMSCH1_DOORBELL_RANGE__SIZE_MASK 0x001F0000L
+static void nbio_v7_4_query_ras_error_count(struct amdgpu_device *adev,
+ void *ras_error_status);
+
static void nbio_v7_4_remap_hdp_registers(struct amdgpu_device *adev)
{
WREG32_SOC15(NBIO, 0, mmREMAP_HDP_MEM_FLUSH_CNTL,
@@ -314,6 +317,7 @@ static void nbio_v7_4_init_registers(struct amdgpu_device *adev)
static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device *adev)
{
uint32_t bif_doorbell_intr_cntl;
+ struct ras_manager *obj = amdgpu_ras_find_obj(adev, adev->nbio.ras_if);
bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
if (REG_GET_FIELD(bif_doorbell_intr_cntl,
@@ -324,6 +328,12 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
RAS_CNTLR_INTERRUPT_CLEAR, 1);
WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
+ /*
+ * clear error status after ras_controller_intr according to
+ * hw team and count ue number for query
+ */
+ nbio_v7_4_query_ras_error_count(adev, &obj->err_data);
+
DRM_WARN("RAS controller interrupt triggered by NBIF error\n");
/* ras_controller_int is dedicated for nbif ras error,
--
2.28.0